project-ContemPlace: Instructions file for Claude Code

CLAUDE.md

project-ContemPlace CLAUDE.md is an instructions file for Claude Code from freegyes/project-ContemPlace. It costs 4,140 tokens per session, scanned A, original, MIT.

Repository instructions for ContemPlace, a commonplace book that turns raw messages from Telegram or other MCP clients into searchable, linked knowledge in a database. MCP is a standard way for AI tools to connect to external services.

In plain words
What is it for?
Understanding and developing the message-capture system, AI processing, vector search, knowledge links, Telegram bot, database, file storage, and scheduled gardening pipeline.
Why use it?
They explain the project's unusual capture workflow, technology choices, and architecture so the coding assistant can make changes that preserve raw input and automated organisation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is freegyes/project-ContemPlace's own configuration. It tells Claude Code how to work on project-ContemPlace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything project-ContemPlace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to freegyes/project-ContemPlace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/freegyes/project-ContemPlace/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/freegyes/project-ContemPlace

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for project-ContemPlace CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/freegyes/project-contemplace/claude-md/github.svg)](https://agentmods.dev/instructions/freegyes/project-contemplace/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/freegyes/project-contemplace/claude-md"><img src="https://agentmods.dev/badge/instructions/freegyes/project-contemplace/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-ContemPlace CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/freegyes/project-contemplace/claude-md"><img src="https://agentmods.dev/badge/instructions/freegyes/project-contemplace/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,140 This file is loaded in full into every session.
When invoked 4,140 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.04140 $0.04140
Opus 5 $0.02070 $0.02070
Sonnet 5 $0.00828 $0.00828
Haiku 4.5 $0.00414 $0.00414

Measured 9d ago against content hash 1eeb00506250, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

project-ContemPlace CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with code in this repository.

What This Is

ContemPlace is a modern commonplace book that auto-gardens into an MCP-connected PKM system. Capture idea fragments from Telegram or any MCP client — the system structures, embeds, and links them into a searchable knowledge graph in Postgres (pgvector). A nightly gardening pipeline surfaces similarity connections and detects topic clusters.

It is not a notes app. Notes are written by the capture agent, not the user. Users send raw input and receive confirmations. The raw input is always preserved alongside the structured fragment.

Stack

Layer Technology
Database Supabase (Postgres 16 + pgvector)
Compute Cloudflare Workers (TypeScript, V8 runtime)
Object storage Cloudflare R2 (photo attachments from Telegram)
Capture interface Telegram bot (webhook-based, not polling)
AI gateway OpenRouter (https://openrouter.ai/api/v1), OpenAI-compatible SDK
Embeddings openai/text-embedding-3-small — 1536 dimensions (default, no truncation). Configurable via EMBED_MODEL env var.
Capture LLM anthropic/claude-haiku-4-5 — configurable via CAPTURE_MODEL env var
Dashboard Cloudflare Pages (vanilla HTML/CSS/ES-modules SPA) + Dashboard API Worker (contemplace-dashboard-api)

Architecture

Cloudflare Workers handles the Telegram webhook. Supabase is the database only — no Edge Functions.

The capture flow is async: the Worker returns 200 to Telegram immediately, then processes in the background via ctx.waitUntil().

Single capture path: The Telegram Worker delegates capture to the MCP Worker via a Cloudflare Service Binding (in-process RPC, no HTTP hop). The capture pipeline lives in mcp/src/pipeline.ts — one source of truth for all gateways.

On-demand gardening: The MCP Worker triggers the Gardener via a second Service Binding (env.GARDENER_SERVICE.trigger()) — in-process RPC, same pattern as capture. CF Workers on the same zone cannot call each other via HTTP (error 1042), so Service Bindings are the only option for Worker-to-Worker communication.

Read the full file on GitHub · 256 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 256 lines · 4,140 tokens per session scan A 1eeb00506250

Subscribe to this mod's changes

project-ContemPlace CLAUDE.md is an instructions file published in the GitHub repository freegyes/project-ContemPlace (3 stars, last pushed 5mo ago), licensed MIT. It adds 4,140 tokens to every session, about $0.0207 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens